Subject-driven text-to-image generation has demonstrated remarkable advancements in its ability to learn and capture characteristics of a subject using only a limited number of images. However, existing methods commonly rely on high-quality images for training and often struggle to generate reasonable images when the input images are blemished by artifacts. This is primarily attributed to the inadequate capability of current techniques in distinguishing subject-related features from disruptive artifacts. In this paper, we introduce ArtiFade to tackle this issue and successfully generate high-quality artifact-free images from blemished datasets. Specifically, ArtiFade exploits fine-tuning of a pre-trained text-to-image model, aiming to remove artifacts. The elimination of artifacts is achieved by utilizing a specialized dataset that encompasses both unblemished images and their corresponding blemished counterparts during fine-tuning. ArtiFade also ensures the preservation of the original generative capabilities inherent within the diffusion model, thereby enhancing the overall performance of subject-driven methods in generating high-quality and artifact-free images. We further devise evaluation benchmarks tailored for this task. Through extensive qualitative and quantitative experiments, we demonstrate the generalizability of ArtiFade in effective artifact removal under both in-distribution and out-of-distribution scenarios.

Research indicates that a significant number of individuals are in a suboptimal auditory health state , yet their auditory function can potentially be improved through auditory training. To raise awareness of auditory health issues, auditory training apps should provide effective yet accessible training methods alongside engaging mechanisms that motivate users to adopt and sustain auditory training habits, ultimately facilitating self-directed auditory health management. Current auditory training apps overlook the importance of user needs and motivation, as well as the relationship between the two, leading to low engagement and retention rates. We document the specific needs of both normal-hearing and mildly hearing-impaired users and analyze physiological data collected during auditory training tasks. Through lab experiment study, we provide quantitative evidence supporting the effectiveness of the auditory training method used in this study. The findings indicate that audiovisual-based auditory training contributes to improved auditory performance. Building on these insights, we develop an auditory training app prototype that integrates gamification and narrative design into the auditory training app prototype, and examine their impact on user motivation and engagement. Furthermore, based on the results, we propose design recommendations for future auditory training app development, emphasizing the need to align training effectiveness with user motivation and engagement strategies.

Deep learning, such as convolutional neural networks (CNNs), has been utilized in a number of cloud-based Internet of Things (IoT) applications. Security and privacy are two key considerations in any commercial deployment. Fully homomorphic encryption (FHE) is a popular privacy protection approach, and there have been attempts to integrate FHE with CNNs. However, a simple integration may lead to inefficiency in single-user services and fail to support many of the requirements in real-time applications. In this article, we propose a novel confused modulo projection-based FHE algorithm (CMP-FHE) that is designed to support floating-point operations. Then, we developed a parallelized runtime library based on CMP-FHE and compared it with the widely employed FHE library. Our results show that our library achieves faster speeds. Furthermore, we compared it with the state-of-the-art confused modulo projection-based library and the results demonstrated a speed improvement of 841.67 to 3056.25 times faster. Additionally, we construct a real-time homomorphic CNN (RT-HCNN) under the ciphertext-based framework using CMP-FHE, as well as using graphics processing units (GPUs) to facilitate acceleration. To demonstrate utility, we evaluate the proposed approach on the MNIST data set. Findings demonstrate that our proposed approach achieves a high accuracy rate of 99.13%. Using GPUs acceleration for ciphertext prediction results in us achieving a single prediction time of 79.5 ms. This represents the first homomorphic CNN capable of supporting real-time application and is approximately 58 times faster than Microsoft’s Lola scheme.